linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Oded Gabbay <ogabbay@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: Dani Liberman <dliberman@habana.ai>
Subject: [PATCH 05/12] habanalabs: fix race condition in multi CS completion
Date: Sun, 28 Nov 2021 21:34:28 +0200	[thread overview]
Message-ID: <20211128193435.266534-5-ogabbay@kernel.org> (raw)
In-Reply-To: <20211128193435.266534-1-ogabbay@kernel.org>

From: Dani Liberman <dliberman@habana.ai>

Race example scenario:
1. User have 2 threads that waits on multi CS:
   - thread_0 waits on QID 0 and uses multi CS context 0.
   - thread_1 waits on QID 1 and uses multi CS context 1.
2. thread_1 got completion and release multi CS context 1.
3. CS related to multi CS of thread_0 starts executing
   complete_multi_cs function, the first iteration of the loop
   completes the multi CS of thread_0, hence multi CS context 0
   is released.
4. thread_1 waits on QID 1 and uses multi CS context 0.
5. thread_0 waits on QID 0 and uses multi CS context 1.
6. The second iterattion of the loop (from step 3) starts, which
   means, start checking multi CS context 1:
   - multi CS contetxt is being used by thread_0 waiting on QID 0.
   - The fence of the CS (still CS from step 3) has QID map the same
     as the multi CS context 1.
   - multi CS context 1 (thread_0) gets completion on CS that triggered
     already thread_0 (with multi CS context 0) and is no longer
     being waited on.

Fixed by exiting the loop in complete_multi_cs after getting completion

Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/misc/habanalabs/common/command_submission.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index c1fd4ba14c60..4e893364a3cc 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -545,6 +545,13 @@ static void complete_multi_cs(struct hl_device *hdev, struct hl_cs *cs)
 			 * mcs fences.
 			 */
 			fence->mcs_handling_done = true;
+			/*
+			 * Since CS (and its related fence) can be associated with only one
+			 * multi CS context, once it triggered multi CS completion no need to
+			 * continue checking other multi CS contexts.
+			 */
+			spin_unlock(&mcs_compl->lock);
+			break;
 		}
 
 		spin_unlock(&mcs_compl->lock);
-- 
2.25.1


  parent reply	other threads:[~2021-11-28 19:37 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-28 19:34 [PATCH 01/12] habanalabs: fix soft reset accounting Oded Gabbay
2021-11-28 19:34 ` [PATCH 02/12] habanalabs: rename late init after reset function Oded Gabbay
2021-11-28 19:34 ` [PATCH 03/12] habanalabs/gaudi: return EPERM on non hard-reset Oded Gabbay
2021-11-28 19:34 ` [PATCH 04/12] habanalabs: move device boot warnings to the correct location Oded Gabbay
2021-11-28 19:34 ` Oded Gabbay [this message]
2021-11-28 19:34 ` [PATCH 06/12] habanalabs: add more info ioctls support during reset Oded Gabbay
2021-11-28 19:34 ` [PATCH 07/12] habanalabs: add power information type to POWER_GET packet Oded Gabbay
2021-11-28 19:34 ` [PATCH 08/12] habanalabs: change misleading IRQ warning during reset Oded Gabbay
2021-11-28 19:34 ` [PATCH 09/12] habanalabs: handle events during soft-reset Oded Gabbay
2021-11-28 19:34 ` [PATCH 10/12] habanalabs: skip read fw errors if dynamic descriptor invalid Oded Gabbay
2021-11-28 19:34 ` [PATCH 11/12] habanalabs: add SOB information to signal submission uAPI Oded Gabbay
2021-11-28 19:34 ` [PATCH 12/12] habanalabs: enable access to info ioctl during hard reset Oded Gabbay

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20211128193435.266534-5-ogabbay@kernel.org \
    --to=ogabbay@kernel.org \
    --cc=dliberman@habana.ai \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).